Alibaba's Qwen has grown from a modest 7B-parameter model into a sprawling family reaching 2.4 trillion parameters, spanning language, vision, audio, and multimodal generation that increasingly shapes the open-weight AI landscape.
New research probes how robust multimodal fact-checking systems are when claims are rewritten by LLMs. The findings reveal fragility in verification pipelines that could let manipulated or synthetic content slip past automated authenticity checks.
Generative Adversarial Networks power much of today's synthetic media, from deepfakes to AI-generated faces. Here's a technical breakdown of how GANs pit two neural networks against each other to learn the art of creating realistic new data.
Suno, the popular AI music generator, is rolling out a beta speech feature that turns text into spoken audio, expanding from song creation into full synthetic voice generation and raising fresh questions about audio authenticity.
A new research paper proposes manifold-constrained initial noise optimization, a lightweight method to align diffusion-based generative models with human preferences and reward signals without costly fine-tuning.
A new arXiv paper argues that defining the null hypothesis is the hardest part of detecting memorization in generative models, proposing exact statistical tests to rigorously determine when a model is reproducing its training data.
A new DeBERTa-based detector tackles AI-generated text under adversarial paraphrasing and realistic deployment conditions, addressing a critical blind spot in synthetic media authentication.
New research reveals that fairness evaluations of adapted speech LLMs can swing dramatically based on a single random training seed — exposing a reproducibility blind spot that affects how we trust voice and audio AI systems.
New research shows how targeted rewriting can forge the stylistic fingerprints that identify which LLM wrote a text, undermining authorship attribution and raising fresh concerns for synthetic media detection.
Researchers have built an AI 'mind-reading' system that reconstructs the images a person is viewing using brain scan data, blending neural decoding with generative models in a striking new frontier for synthetic media.
AI video agents and video generation APIs solve different problems in synthetic media pipelines. Here's how they differ architecturally, when to use each, and what it means for building scalable AI video workflows.
New empirical research examines whether AI-generated social media posts can corrupt disaster social sensing systems — and whether current detection methods can tell synthetic crisis content from the real thing.